Claude-code-tools recover-context
Extract full context of the last task from the most recent parent session
install
source · Clone the upstream repo
git clone https://github.com/pchalasani/claude-code-tools
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/pchalasani/claude-code-tools "$T" && mkdir -p ~/.claude/skills && cp -r "$T/plugins/aichat/skills/recover-context" ~/.claude/skills/pchalasani-claude-code-tools-recover-context && rm -rf "$T"
manifest:
plugins/aichat/skills/recover-context/SKILL.mdsource content
recover-context
Use this skill to extract context from a parent session when a session lineage is present (shown in the first user message of this conversation).
Instructions
-
Identify the most recent parent session from the lineage chain (the last file in the chronological list).
-
Use sub-agents to explore (to avoid bloating your own context):
- If you have the Task tool with subagent support, use the
subagent (subagent_type:session-searcher
) to analyze the most recent sessionsession-searcher - If sub-agents are NOT available, use the
skill insteadaichat:session-search
- If you have the Task tool with subagent support, use the
-
Extract the following from the most recent session:
- What was the last task being worked on?
- What was the current state of that task (completed, in-progress, blocked)?
- Any pending items or next steps mentioned?
- Key decisions made or approaches chosen
-
Also check for associated documents:
- Issue specs or task descriptions referenced in the session
- Any markdown files created during that session (check WORKLOG/, issues/, etc.)
- Code files that were being modified
-
Report back concisely:
- State your understanding of the task context
- List any files you found that are relevant
- Ask the user how they'd like to proceed
Example Sub-agent Prompt
If using the Task tool with
session-searcher subagent:
Analyze the session file at [path from lineage] and extract: 1. The last task being worked on (look at the final 20-30 messages) 2. Current state of that task 3. Any referenced markdown files (issue specs, work logs, etc.) 4. Pending next steps or blockers Return a concise summary.
Constraints
- Do NOT read large session files directly into your own context
- ALWAYS delegate to sub-agents or the session-search skill
- Keep your summary concise - the user knows what they were working on
- Focus on the LAST task, not the entire session history